© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28304
    Prev
    Next
    INDEX
    Explanations

    requires

    np_acts-logits-general · gemini-2.5-flash-lite

    requires skill or effort

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     പഞ്ചായ
    0.48
    ಿಸಿದ್ದ
    0.47
    bookmarks
    0.45
     staffers
    0.45
    옐
    0.43
     defaul
    0.42
     παι
    0.42
    できなかった
    0.42
    겠지만
    0.41
    츈
    0.41
    POSITIVE LOGITS
     wymaga
    0.70
     requiere
    0.66
    Requires
    0.65
     требует
    0.62
     requires
    0.61
     require
    0.58
     requieren
    0.57
     wymag
    0.57
     Requires
    0.57
     nécessite
    0.57
    Activations Density 0.158%

    No Known Activations